CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-beats

Writing, exploit——把原始素材组装成一段节拍旅程,在某个 beat 依赖一个术语之前先把它 grounded。

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/writing-beats/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted, lean instruction-only skill: the beat-by-beat workflow is precisely sequenced with user-approval checkpoints, disk-reread discipline, and edit-preservation rules, and the supporting sections stay tightly on-topic. Its only weaknesses are minor — slight redundancy around the grounded-concept ledger and the absence of a sample beat to calibrate against.

DimensionReasoningScore

Conciseness

The body is dense and instructive ("它只做一件事:设定场景、落下一个观点、提出问题……然后停下") with no explanations of concepts Claude already knows; the only trimmable redundancy is the grounded-concept ledger instruction appearing both in the what-to-do steps ("记下每个 beat 新 grounded 了哪些概念") and again in the Grounding section ("维护一份到目前为止已 grounded 内容的清单").

4 / 5

Actionability

For an instruction-only skill the guidance is concrete and directly executable — "只把**那个 beat**写入文章文件……写完就停", "每次写入前都从磁盘重新读取文章文件。绝对保留用户 edits", "如果用户没有说明文章保存路径,只询问一次并记住路径" — but there is no worked example of a candidate beat to calibrate output against, which keeps it just short of fully executable.

4 / 5

Workflow Clarity

A clear numbered sequence (1–5) with a loop ("循环步骤 3-5") and real checkpoints: beats shown to the user before writing ("在写入文章文件之前先把这些 beats 展示给用户"), rereading from disk before each write, and handling rewrite requests ("就地编辑,别动其余部分"). The loop instruction "循环步骤 3-5" is self-referential since step 5 is itself the loop step, a minor gap; not a destructive/batch operation so no validation cap applies.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the ~60-line body is cleanly split into <what-to-do> and <supporting-info> with well-labeled sections (Grounding, What is a beat, Pulling from the pile, Ending the journey, Writing rhythm), and the single internal reference [Grounding](#grounding) resolves to a real section. Per the simple-skill guidance, well-organized sections with no need for external references score 5.

5 / 5

Total

17

/

20

Passed

Description

42%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys an unusual but real capability, yet it is written in the skill's own invented vocabulary rather than user-facing language, and it completely lacks any 'when to use this' trigger guidance. A user (or the model) would struggle to know when this skill applies or to distinguish it from generic writing help.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to turn raw notes or source material into an article/essay, beat by beat, with user choosing the direction at each step.'

Replace or gloss the jargon terms ('exploit', 'beat journey', 'grounded') with plain-language action verbs, e.g. 'Drafts an article incrementally from a pile of raw material, introducing each concept before any later section depends on it.'

Include natural trigger terms users would actually say — 'draft', 'essay', 'article', 'turn my notes into a post', 'write from source material' — to improve both trigger matching and distinctiveness from generic writing skills.

DimensionReasoningScore

Specificity

The description names the writing domain and 1-2 actions ("把原始素材组装成一段节拍旅程", "在某个 beat 依赖一个术语之前先把它 grounded"), but these are phrased in invented craft jargon ('beat journey', 'grounded') rather than plain concrete actions, and coverage is not comprehensive.

3 / 5

Completeness

The 'what' is present (assembles raw material into a beat-by-beat journey, grounding terms before beats depend on them), but the 'when' is entirely absent — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"Writing" is a single generic keyword, while "exploit", "beat", "grounded", and "raw material" are jargon users would not naturally say when requesting this skill; natural phrases like 'draft an essay from my notes' are missing.

2 / 5

Distinctiveness Conflict Risk

The lead term "Writing" is broad and would overlap with any general writing/drafting skill, though the distinctive concepts ('beat journey', 'grounding', raw-material pile) narrow it somewhat; it could still trigger for the wrong writing skill.

3 / 5

Total

11

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vinvcn/mattpocock-skills-zh-CN
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.